Graph isomorphisms effect structure optimization of neural networks

被引:1
|
作者
Igel, C [1 ]
Stagge, P [1 ]
机构
[1] Ruhr Univ Bochum, Inst Neuroinformat, D-44780 Bochum, Germany
关键词
D O I
10.1109/IJCNN.2002.1005459
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Concepts from graph theory and molecular evolution are proposed for analyzing effects of redundancy induced by graph isomorphisms on structure optimization of neural networks. It is demonstrated that a graph database that considers isomorphisms can drastically reduce the number of evaluations in an evolutionary structure optimization process.
引用
收藏
页码:142 / 147
页数:4
相关论文
共 50 条
  • [21] GraphNET: Graph Neural Networks for routing optimization in Software Defined Networks
    Swaminathan, Avinash
    Chaba, Mridul
    Sharma, Deepak Kumar
    Ghosh, Uttam
    COMPUTER COMMUNICATIONS, 2021, 178 : 169 - 182
  • [22] Graph Neural Networks for Joint Communication and Sensing Optimization in Vehicular Networks
    Li, Xuefei
    Chen, Mingzhe
    Liu, Yuchen
    Zhang, Zhilong
    Liu, Danpu
    Mao, Shiwen
    IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2023, 41 (12) : 3893 - 3907
  • [23] Structure optimization of neural networks with the A*-algorithm
    Doering, A
    Galicki, M
    Witte, H
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 1997, 8 (06): : 1434 - 1445
  • [24] Structure optimization of neural networks with the A*-algorithm
    Friedrich Schiller Univ, Jena, Germany
    IEEE Trans Neural Networks, 6 (1434-1445):
  • [25] Graph Structure Reshaping Against Adversarial Attacks on Graph Neural Networks
    Wang, Haibo
    Zhou, Chuan
    Chen, Xin
    Wu, Jia
    Pan, Shirui
    Li, Zhao
    Wang, Jilong
    Yu, Philip S.
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2024, 36 (11) : 6344 - 6357
  • [26] Knowledge Distillation Improves Graph Structure Augmentation for Graph Neural Networks
    Wu, Lirong
    Lin, Haitao
    Huang, Yufei
    Li, Stan Z.
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [27] Self-Supervised Graph Structure Refinement for Graph Neural Networks
    Zhao, Jianan
    Wen, Qianlong
    Ju, Mingxuan
    Zhang, Chuxu
    Ye, Yanfang
    arXiv, 2022,
  • [28] Differentially private graph neural networks for graph classification and its adaptive optimization
    Li, Yong
    Song, Xiao
    Gong, Kaiqi
    Liu, Songsong
    Li, Wenxin
    EXPERT SYSTEMS WITH APPLICATIONS, 2025, 263
  • [29] Applying Graph Neural Networks to the Decision Version of Graph Combinatorial Optimization Problems
    Jovanovic, Raka
    Palk, Michael
    Bayhan, Sertac
    Voss, Stefan
    IEEE ACCESS, 2023, 11 : 38534 - 38547
  • [30] Structure optimization of neural networks for evolutionary design optimization
    Hüsken, M
    Jin, Y
    Sendhoff, B
    SOFT COMPUTING, 2005, 9 (01) : 21 - 28